Search NASA⌕ Search

SEARCH · Search NASA

Results for “Many-core”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 163 records · Page 9

F3D Image Processing and Analysis for Many - and Multi-core Platforms

F3D is written in OpenCL, so it achieve[sic] platform-portable parallelism on modern mutli-core CPUs and many-core GPUs. The interface and mechanims to access F3D core are written in Java as a plugin for Fiji/ImageJ to deliver several key image-processing algorithms necessary to remove artifacts from micro-tomography data. The algorithms consist of data parallel aware filters that can efficiently utilizes[sic] resources and can work on out of core datasets and scale efficiently across multiple accelerators. Optimizing for data parallel filters, streaming out of core datasets, and efficient resource and memory and data managements over complex execution sequence of filters greatly expedites any scientific workflow with image processing requirements. F3D performs several different types of 3D image processing operations, such as non-linear filtering using bilateral filtering and/or median filtering and/or morphological operators (MM). F3D gray-level MM operators are one-pass constant time methods that can perform morphological transformations with a line-structuring element oriented in discrete directions. Additionally, MM operators can be applied to gray-scale images, and consist of two parts: (a) a reference shape or structuring element, which is translated over the image, and (b) a mechanism, or operation, that defines the comparisons to be performed between the image and the structuring element. This tool provides a critical component within many complex pipelines such as those for performing automated segmentation of image stacks. F3D is also called a "descendent" of Quant-CT, another software we developed in the past. These two modules are to be integrated in a next version. Further details were reported in: D.M. Ushizima, T. Perciano, H. Krishnan, B. Loring, H. Bale, D. Parkinson, and J. Sethian. Structure recognition from high-resolution images of ceramic composites. IEEE International Conference on Big Data, October 2014.

Source record↗

Large-Scale Compute-Intensive Analysis via a Combined In-situ and Co-scheduling Workflow Approach

Large-scale simulations can produce tens of terabytes of data per analysis cycle, complicating and limiting the efficiency of workflows. Traditionally, outputs are stored on the file system and analyzed in post-processing. With the rapidly increasing size and complexity of simulations, this approach faces an uncertain future. Trending techniques consist of performing the analysis in situ, utilizing the same resources as the simulation, and/or off-loading subsets of the data to a compute-intensive analysis system. We introduce an analysis framework developed for HACC, a cosmological N-body code, that uses both in situ and co-scheduling approaches for handling Petabyte-size outputs. An initial in situ step is used to reduce the amount of data to be analyzed, and to separate out the data-intensive tasks handled off-line. The analysis routines are implemented using the PISTON/VTK-m framework, allowing a single implementation of an algorithm that simultaneously targets a variety of GPU, multi-core, and many-core architectures.

Big data↗

Scalable Out-of-Core Solvers on Xeon Phi Cluster

This paper documents the implementation of a distributive out-of-core (OOC) solver for performing LU and Cholesky factorizations of a large dense matrix on clusters of many-core programmable co-processors. The out-of- core algorithm combines both the left-looking and right-looking schemes aimed to minimize the movement of data between the CPU host and the co-processor, optimizing data locality as well as computing throughput. The OOC solver is built to align with the format of the ScaLAPACK software library, making it readily portable to any existing codes using ScaLAPACK. A runtime analysis conducted on Beacon (an Intel Xeon plus Intel Xeon Phi cluster which composed of 48 nodes of multi-core CPU and MIC) at the Na- tional Institute for Computational Sciences is presented. Comparison of the performance on the Intel Xeon Phi and GPU clusters are also provided.

D'Azevedo, Ed F↗

Introducing Argonne’s Theta Supercomputer

Theta, the Argonne Leadership Computing Facility’s (ALCF) new Intel-Cray supercomputer, is officially open to the research community. Theta’s massively parallel, many-core architecture puts the ALCF on the path to Aurora, the facility’s future Intel-Cray system. Capable of nearly 10 quadrillion calculations per second, Theta enables researchers to break new ground in scientific investigations that range from modeling the inner workings of the brain to developing new materials for renewable energy applications.

97 MATHEMATICS AND COMPUTING↗

Understanding the I/O Performance Gap Between Cori KNL and Haswell

The Cori system at NERSC has two compute partitions with different CPU architectures: a 2,004 node Haswell partition and a 9,688 node KNL partition, which ranked as the 5th most powerful and fastest supercomputer on the November 2016 Top 500 list. The compute partitions share a common storage configuration, and understanding the IO performance gap between them is important, impacting not only to NERSC/LBNL users and other national labs, but also to the relevant hardware vendors and software developers. In this paper, we have analyzed performance of single core and single node IO comprehensively on the Haswell and KNL partitions, and have discovered the major bottlenecks, which include CPU frequencies and memory copy performance. We have also extended our performance tests to multi-node IO and revealed the IO cost difference caused by network latency, buffer size, and communication cost. Overall, we have developed a strong understanding of the IO gap between Haswell and KNL nodes and the lessons learned from this exploration will guide us in designing optimal IO solutions in many-core era.

97 MATHEMATICS AND COMPUTING↗

Considerations on the Use of Custom Accelerators for Big Data Analytics

Accelerators, including Graphic Processing Units (GPUs) for gen- eral purpose computation, many-core designs with wide vector units (e.g., Intel Phi), have become a common component of many high performance clusters. The appearance of more stable and reliable tools tools that can automatically convert code written in high-level specifications with annotations (such as C or C++) to hardware de- scription languages (High-Level Synthesis - HLS), is also setting the stage for a broader use of reconfigurable devices (e.g., Field Pro- grammable Gate Arrays - FPGAs) in high performance system for the implementation of custom accelerators, helped by the fact that new processors include advanced cache-coherent interconnects for these components. In this chapter, we briefly survey the status of the use of accelerators in high performance systems targeted at big data analytics applications. We argue that, although the progress in the use of accelerators for this class of applications has been sig- nificant, differently from scientific simulations there still are gaps to close. This is particularly true for the ”irregular” behaviors exhibited by no-SQL, graph databases. We focus our attention on the limits of HLS tools for data analytics and graph methods, and discuss a new architectural template that better fits the requirement of this class of applications. We validate the new architectural templates by mod- ifying the Graph Engine for Multithreaded System (GEMS) frame- work to support accelerators generated with such a methodology, and testing with queries coming from the Lehigh University Benchmark (LUBM). The architectural template enables better supporting the task and memory level parallelism present in graph methods by sup- porting a new control model and a enhanced memory interface. We show that out solution allows generating parallel accelerators, pro- viding speed ups with respect to conventional HLS flows. We finally draw conclusions and present a perspective on the use of reconfig- urable devices and Design Automation tools for data analytics.

Data Analytics↗

Parallelized and Vectorized Tracking Using Kalman Filters with CMS Detector Geometry and Events

The High-Luminosity Large Hadron Collider at CERN will be characterized by greater pileup of events and higher occupancy, making the track reconstruction even more computationally demanding. Existing algorithms at the LHC are based on Kalman filter techniques with proven excellent physics performance under a variety of conditions. Starting in 2014, we have been developing Kalman-filter-based methods for track finding and fitting adapted for many-core SIMD processors that are becoming dominant in high-performance systems. This paper summarizes the latest extensions to our software that allow it to run on the realistic CMS-2017 tracker geometry using CMSSW-generated events, including pileup. The reconstructed tracks can be validated against either the CMSSW simulation that generated the hits, or the CMSSW reconstruction of the tracks. In general, the code's computational performance has continued to improve while the above capabilities were being added. We demonstrate that the present Kalman filter implementation is able to reconstruct events with comparable physics performance to CMSSW, while providing generally better computational performance. Further plans for advancing the software are discussed.

Cerati, Giuseppe↗

Performance-Portable Particle Advection with VTK-m

Particle advection is the fundamental kernel behind most vector field visualization methods. Yet, the efficient parallel computation of large amounts of particle traces remains challenging. This is exacerbated by the variety of hardware trends in today's HPC arena, including increasing core counts in classical CPUs, many-core designs such as the Intel Xeon Phi, and massively parallel GPUs. The dedicated optimization of a particle advection kernel for each individual target architecture is both time-consuming and error prone. In this paper, we propose a performance-portable algorithm for particle advection. Our algorithm is based on the recently introduced VTK-m system and chiefly relies on its device adapter abstraction. We demonstrate the general portability of our implementation across a wide variety of hardware. Finally, our evaluation shows that our hardware-agnostic algorithm has comparable performance to hardware-specific algorithms.

Pugmire, Dave↗

Speeding up Particle Track Reconstruction in the CMS Detector using a Vectorized and Parallelized Kalman Filter Algorithm

Building particle tracks is the most computationally intense step of event reconstruction at the LHC. With the increased instantaneous luminosity and associated increase in pileup expected from the High-Luminosity LHC, the computational challenge of track finding and fitting requires novel solutions. The current track reconstruction algorithms used at the LHC are based on Kalman filter methods that achieve good physics performance. By adapting the Kalman filter techniques for use on many-core SIMD architectures such as the Intel Xeon and Intel Xeon Phi and (to a limited degree) NVIDIA GPUs, we are able to obtain significant speedups and comparable physics performance. New optimizations, including a dedicated post-processing step to remove duplicate tracks, have improved the algorithm's performance even further. Here we report on the current structure and performance of the code and future plans for the algorithm.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Reconstruction of Charged Particle Tracks in Realistic Detector Geometry Using a Vectorized and Parallelized Kalman Filter Algorithm

One of the most computationally challenging problems expected for the High-Luminosity Large Hadron Collider (HL-LHC) is finding and fitting particle tracks during event reconstruction. Algorithms used at the LHC today rely on Kalman filtering, which builds physical trajectories incrementally while incorporating material e ects and error estimation. Recognizing the need for faster computational throughput, we have adapted Kalman-filterbased methods for highly parallel, many-core SIMD and SIMT architectures that are now prevalent in high-performance hardware. Previously we observed significant parallel speedups, with physics performance comparable to CMS standard tracking, on Intel Xeon, Intel Xeon Phi, and (to a limited extent) NVIDIA GPUs. While early tests were based on artificial events occurring inside an idealized barrel detector, we showed subsequently that our mkFit software builds tracks successfully from complex simulated events (including detector pileup) occurring inside a geometrically accurate representation of the CMS-2017 tracker. Here, we report on advances in both the computational and physics performance of mkFit, as well as progress toward integration with CMS production software. Recently we have improved the overall eciency of the algorithm by preserving short track candidates at a relatively early stage rather than attempting to extend them over many layers. Moreover, mkFit formerly produced an excess of duplicate tracks; these are now explicitly removed in an additional processing step. We demonstrate that with these enhancements, mkFit becomes a suitable choice for the first iteration of CMS tracking, and eventually for later iterations as well. We plan to test this capability in the CMS High Level Trigger during Run 3 of the LHC, with an ultimate goal of using it in both the CMS HLT and oine reconstruction for the HL-LHC CMS tracker.

Cerati, Giuseppe↗

m-CUBES An efficient and portable implementation of multi-dimensional integration for gpus

The task of multi-dimensional numerical integration is frequently encountered in physics and other scientific fields, e.g., in modeling the effects of systematic uncertainties in physical systems and in Bayesian parameter estimation. Multi-dimensional integration is often time-prohibitive on CPUs. Efficient implementation on many-core architectures is challenging as the workload across the integration space cannot be predicted a priori. We propose m-Cubes, a novel implementation of the well-known Vegas algorithm for execution on GPUs. Vegas transforms integration variables followed by calculation of a Monte Carlo integral estimate using adaptive partitioning of the resulting space. m-Cubes improves performance on GPUs by maintaining relatively uniform workload across the processors. As a result, our optimized Cuda implementation for Nvidia GPUs outperforms parallelization approaches proposed in past literature. We further demonstrate the efficiency of m-Cubes by evaluating a six-dimensional integral from a cosmology application, achieving significant speedup and greater precision than the CUBA library's CPU implementation of VEGAS. We also evaluate m-Cubes on a standard integrand test suite. m-Cubes outperforms the serial implementations of the Cuba and GSL libraries by orders of magnitude speedup while maintaining comparable accuracy. Our approach yields a speedup of at least 10 when compared against publicly available Monte Carlo based GPU implementations. In summary, m-Cubes can solve integrals that are prohibitively expensive using standard libraries and custom implementations. A modern C++ interface header-only implementation makes m-Cubes portable, allowing its utilization in complicated pipelines with easy to define stateful integrals. Compatibility with non-Nvidia GPUs is achieved with our initial implementation of m-Cubes using the Kokkos framework.

Sakiotis, Ioannis↗

Algorithmic Improvements for Portable Event-Based Monte Carlo Transport Using the Nvidia Thrust Library

High performance computing environments are progressively moving towards many-core computing architectures. The Los Alamos National Laboratory Trinity machine, available in late 2016, will use both Intel Xeon Haswell processors and Intel Xeon Phi Knights Landing many integrated core (MIC) coprocessors. The Lawrence Livermore National Laboratory Sierra machine, available in 2018, will use an IBM PowerPC architecture along with Nvidia graphics processing units (GPUs). Applications that must work in this supercomputing environment must continue to adapt in order to take advantage of the diverse hardware architectures that are coming. A significant consideration is not only the performance of the application on a given platform but also the portability of the application to other platforms. The algorithmic improvements presented in this paper build upon recently-reported work on event-based Monte Carlo transport in the ALPSMC code that models particle transport in one-dimensional binary stochastic media. That paper discussed the lack of available vectorization in the traditional history-based algorithm used for Monte Carlo transport and presented a data parallel event-based algorithm implemented using the Nvidia Thrust library for portability. The performance of the data parallel event-based algorithm implemented using Thrust was compared to a native CUDA implementation. The conclusions from that work were that the Thrust library abstraction technique caused too significant a loss in performance but that the event-based method was a viable option that should be further investigated. In this paper, we describe algorithmic improvements to the data parallel event-based algorithm previously presented. We made further algorithmic optimizations to the event-based CUDA implementation, most notably: data structure changes, a new conditional particle removal scheme in the event-based process, and the use of multiple GPUs. In addition to improvements to the algorithm, we re-implemented the Thrust version from the now further optimized CUDA version, giving a greater chance for success at a performant abstraction. Finally, we revisited our previous assumptions about the inability of the history-based method to achieve performance on vector style architectures such as the MICs and GPUs, with surprising and promising results. (authors)

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Power Analysis for Applications and Data Centers

A portion of a chapter for the High Performance Parallelism Pearls 2 book. By using the NWPerf and CView software developed and deployed at PNNL administrators and users can visually see the performance, and power used by jobs running on a super computer in near-time.

Affinity↗

A compute-bound formulation of Galerkin model reduction for linear time-invariant dynamical systems

This work aims to advance computational methods for projection-based reduced-order models (ROMs) of linear time-invariant (LTI) dynamical systems. For such systems, current practice relies on ROM formulations expressing the state as a rank-1 tensor (i.e., a vector), leading to computational kernels that are memory bandwidth bound and, therefore, ill-suited for scalable performance on modern architectures. This weakness can be particularly limiting when tackling many-query studies, where one needs to run a large number of simulations. This work introduces a reformulation, called rank-2 Galerkin, of the Galerkin ROM for LTI dynamical systems which converts the nature of the ROM problem from memory bandwidth to compute bound. We present the details of the formulation and its implementation, and demonstrate its utility through numerical experiments using, as a test case, the simulation of elastic seismic shear waves in an axisymmetric domain. We quantify and analyze performance and scaling results for varying numbers of threads and problem sizes. In conclusion, we present an end-to-end demonstration of using the rank-2 Galerkin ROM for a Monte Carlo sampling study. We show that the rank-2 Galerkin ROM is one order of magnitude more efficient than the rank-1 Galerkin ROM (the current practice) and about 970 times more efficient than the full-order model, while maintaining accuracy in both the mean and statistics of the field.

97 MATHEMATICS AND COMPUTING↗

Large-scale GW calculations on pre-exascale HPC systems

The ab initio GW approach is a rigorous Green’s-function-based framework that can be employed to compute electronic excitation properties of a wide variety of materials such as extended systems, molecules, as well as confined and nanostructured materials with a very satisfactory accuracy. However, GW calculations on complex systems are often hindered by the high computational cost associated with the method. Here, in this study, we demonstrate how to significantly speedup GW calculations with a novel algorithm for the computationally intense kernel based on a non-blocking chunked cyclic communication scheme that minimizes latency in MPI messages, allows for overlapping of communication and computation, and improves cache usage in matrix multiplication operations. The optimized version of the code, implemented in the BerkeleyGW software package, is capable of scaling well to the full Cori computer at NERSC (Cray XC40) and achieves over 11 Peta FLOP/s of sustained performance. We showcase our work by performing large-scale GW calculations of defect structures on silicon, which require simulation cells containing over 1700 atoms, and which can now be efficiently executed in just a few minutes on large pre-exascale high-performance computing systems.

97 MATHEMATICS AND COMPUTING↗

Toward performance-portable PETSc for GPU-based exascale systems

The Portable Extensible Toolkit for Scientific computation (PETSc) library delivers scalable solvers for nonlinear time-dependent differential and algebraic equations and for numerical optimization. The PETSc design for performance portability addresses fundamental GPU accelerator challenges and stresses flexibility and extensibility by separating the programming model used by the application from that used by the library, and it enables application developers to use their preferred programming model, such as Kokkos, RAJA, SYCL, HIP, CUDA, or OpenCL, on upcoming exascale systems. Furthermore, a blueprint for using GPUs from PETSc-based codes is provided, and case studies emphasize the flexibility and high performance achieved on current GPU-based systems.

97 MATHEMATICS AND COMPUTING↗

Low-synch Gram–Schmidt with delayed reorthogonalization for Krylov solvers

The parallel strong-scaling of iterative methods is often determined by the number of global reductions at each iteration. Low-synch Gram-Schmidt algorithms are applied here to the Arnoldi algorithm to reduce the number of global reductions and therefore to improve the parallel strong-scaling of iterative solvers for nonsymmetric matrices such as the GMRES and the Krylov-Schur iterative methods. In the Arnoldi context, the factorization is "left-looking" and processes one column at a time. Among the methods for generating an orthogonal basis for the Arnoldi algorithm, the classical Gram-Schmidt algorithm, with reorthogonalization (CGS2) requires three global reductions per iteration. A new variant of CGS2 that requires only one reduction per iteration is presented and applied to the Arnoldi algorithm. Delayed CGS2 (DCGS2) employs the minimum number of global reductions per iteration (one) for a one-column at-a-time algorithm. The main idea behind the new algorithm is to group global reductions by rearranging the order of operations. DCGS2 must be carefully integrated into an Arnoldi expansion or a GMRES solver. Numerical stability experiments assess robustness for Krylov-Schur eigenvalue computations. Performance experiments on the ORNL Summit supercomputer then establish the superiority of DCGS2 over CGS2.

97 MATHEMATICS AND COMPUTING↗

Machine Learning-Based Temperature Prediction for Runtime Thermal Management Across System Components

Elevated temperatures limit the peak performance of systems because of frequent interventions by thermal throttling. Non-uniform thermal states across system nodes also cause performance variation within seemingly equivalent nodes leading to significant degradation of overall performance. In this paper we present a framework for creating a lightweight thermal prediction system suitable for run-time management decisions. We pursue two avenues to explore optimized lightweight thermal predictors. First, we use feature selection algorithms to improve the performance of previously designed machine learning methods. Second, we develop alternative methods using neural network and linear regression-based methods to perform a comprehensive comparative study of prediction methods. We show that our optimized models achieve improved performance with better prediction accuracy and lower overhead as compared with the Gaussian process model proposed previously. Specifically we present a reduced version of the Gaussian process model, a neural network-based model, and a linear regression-based model. Using the optimization methods, we are able to reduce the average prediction errors in the Gaussian process from 4: 2 degrees C to 2: 9 degrees C. We also show that the newly developed models using neural network and Lasso linear regression have average prediction errors of 2: 9 degrees C and 3: 8 degrees C respectively. The prediction overheads are 0.22, 0.097, and 0.026 ms per prediction for reduced Gaussian process, neural network, and Lasso linear regression models, respectively, compared with 0.57 ms per prediction for the previous Gaussian process model. We have implemented our proposed thermal prediction models on a two-node system configuration to help identify the optimal task placement. The task placement identified by the models reduces the average system temperature by up to 11: 9 degrees C without any performance degradation. Furthermore, these models respectively achieve 75, 82.5, and 74.17 percent success rates in correctly pointing to those task placements with better thermal response, compared with 72.5 percent success for the original model in achieving the same objective. Lastly, we extended our analysis to a 16-node system and we were able to train models and execute them in real time to guide task migration and achieve on average 17 percent reduction in the overall system cooling power.

97 MATHEMATICS AND COMPUTING↗